Information processing apparatus

Abstract

An information processing apparatus includes a processor configured to receive a narrowing condition designated upon a search request of a content, create a sentence which uses a more detailed expression of an expression described in the narrowing condition and indicates details of the content or select the sentence from sentence candidates prepared in advance, and present the created or selected sentence as a search result of the content.

What is claimed is: 
     
         1 . An information processing apparatus comprising:
 a processor configured to
 receive a narrowing condition designated upon a search request of a content, 
 create a sentence which uses a more detailed expression of an expression described in the narrowing condition and indicates details of the content or select the sentence from sentence candidates prepared in advance, and 
 present the created or selected sentence as a search result of the content. 
   
     
     
         2 . The information processing apparatus according to  claim 1 , wherein
 the detailed expression includes a compound word including the expression described in the narrowing condition.   
     
     
         3 . The information processing apparatus according to  claim 1 , wherein
 the processor is configured to, in a case where a sentence using a more detailed expression of an expression described in the narrowing condition is not provided or creation of the sentence is not possible, present a sentence including details of the content related to a category other than a category to which the expression belongs.   
     
     
         4 . The information processing apparatus according to  claim 2 , wherein
 the processor is configured to, in a case where a sentence using a more detailed expression of an expression described in the narrowing condition is not provided or creation of the sentence is not possible, present a sentence including details of the content related to a category other than a category to which the expression belongs.   
     
     
         5 . The information processing apparatus according to  claim 1 , wherein
 the processor is configured to determine whether to use or change the presented sentence based on a record in which the presented sentence has been selected.   
     
     
         6 . The information processing apparatus according to  claim 5 , wherein
 the processor is configured to
 present each of a plurality of sentences as a search result of the content, and 
 present the sentence of which the number of selections is largest among the plurality of the presented sentences, as the search result of the content when a narrowing condition including the expression described in the narrowing condition is received. 
   
     
     
         7 . The information processing apparatus according to  claim 1 , wherein
 the processor is configured to
 use, as inputs, content information including details of a content as a narrowing target by the narrowing condition, a sentence explaining details of the content, and information indicating whether or not the sentence is associated with the content, and input a plurality of sets including the content information and sentence candidates for the sentence explaining the details of the content, to a relevance estimation model which is learned to output a relevance between the content corresponding to the input content information and the input sentence, and 
 present the sentence candidate having a highest relevance among the plurality of the input sentence candidates, as a search result of the content. 
   
     
     
         8 . The information processing apparatus according to  claim 7 , wherein
 the processor is configured to
 acquire a first relevance by inputting, to the relevance estimation model, the set including the content information including the details of the content as the narrowing target by the narrowing condition and the sentence explaining the details of the content as the narrowing target by the narrowing condition, 
 acquire a second relevance by inputting, to the relevance estimation model, a set including content information including details of a content other than the content as the narrowing target by the narrowing condition and the sentence explaining the details of the content as the narrowing target by the narrowing condition, and 
 not to present the sentence to a user in a case where there is no predetermined difference between the acquired first relevance and the acquired second relevance.